Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf30656975a7ced594f94b07a0f452f9bed705b5e96edcc572d8bdc7909d636
+oid sha256:25044a30b4b9e38086b51eba7f4a265c7ca562d1cacbccec8f8a73ed56568bd7
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c59ddd4a6c30e1796d13bac686374e0b10e6cf8bec72d08fd73735c9de4449f
+oid sha256:6a57ee48b88d94d905afb7fdd8651625f0ad567526e3400890b9377613bebca1
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3ee690ad88b56c8223e3bf83d50e37e8f858cadaf0e44c5eac6f2d3f098a1f
+oid sha256:0224f484e5bfbab7c30ddcc29fc1c1bfdbd095d7e88be12d43d0cd40c26c884f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
+oid sha256:043092824777602976966449c2a2a96527a878ad10507a3b4d0f461ea2b8d14e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3237847089767456,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.16553246275519587,
+  "best_metric": 1.3218564987182617,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.18392495861688432,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 17.403,
       "eval_steps_per_second": 4.362,
       "step": 450
+    },
+    {
+      "epoch": 0.16921096192753357,
+      "grad_norm": 0.7757034301757812,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 1.4375,
+      "step": 460
+    },
+    {
+      "epoch": 0.17288946109987124,
+      "grad_norm": 0.7832618951797485,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 1.339,
+      "step": 470
+    },
+    {
+      "epoch": 0.17656796027220895,
+      "grad_norm": 0.7737963795661926,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 1.3189,
+      "step": 480
+    },
+    {
+      "epoch": 0.18024645944454662,
+      "grad_norm": 0.8774094581604004,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 1.267,
+      "step": 490
+    },
+    {
+      "epoch": 0.18392495861688432,
+      "grad_norm": 1.0865882635116577,
+      "learning_rate": 0.0,
+      "loss": 1.2489,
+      "step": 500
+    },
+    {
+      "epoch": 0.18392495861688432,
+      "eval_loss": 1.3218564987182617,
+      "eval_runtime": 65.6585,
+      "eval_samples_per_second": 17.439,
+      "eval_steps_per_second": 4.371,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.9981238550528e+16,
+  "total_flos": 8.886804283392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null